相关论文: MixGRPO: Unlocking Flow-based GRPO Efficiency with…

3D Gaussian Splatting, known for enabling high-quality static scene reconstruction with fast rendering, is increasingly being applied to multi-view dynamic scene reconstruction. A common strategy involves learning a deformation field to…

Modern optical flow methods make use of salient scene feature points detected and matched within the scene as a basis for sparse-to-dense optical flow estimation. Current feature detectors however either give sparse, non uniform point…

Diffusion policies are expressive yet incur high inference latency. Flow Matching (FM) enables one-step generation, but integrating it into Maximum Entropy Reinforcement Learning (MaxEnt RL) is challenging: the optimal policy is an…

The rapid development of large language models (LLMs) has driven the demand for more efficient optimization techniques. Among these, the Lookahead family of optimizers employs a two-loop framework, maintaining fast and slow sets of model…

Application of the multi-objective particle swarm optimisation (MOPSO) algorithm to design of water distribution systems is described. An earlier MOPSO algorithm is augmented with (a) local search, (b) a modified strategy for assigning the…

Aligning Large Language Models (LLMs) with human feedback is crucial for their development. Existing preference optimization methods such as DPO and KTO, while improved based on Reinforcement Learning from Human Feedback (RLHF), are…

Distribution system operators (DSO) world-wide foresee a rapid roll-out of distributed energy resources. From the system perspective, their reliable and cost effective integration requires accounting for their physical properties in…

Distributed optimization is essential for training large models on large datasets. Multiple approaches have been proposed to reduce the communication overhead in distributed training, such as synchronizing only after performing multiple…

Face retouching requires removing subtle imperfections while preserving unique facial identity features, in order to enhance overall aesthetic appeal. However, existing methods suffer from a fundamental trade-off. Supervised learning on…

We present DeFlow, a decoupled offline RL framework that leverages flow matching to faithfully capture complex behavior manifolds. Optimizing generative policies is computationally prohibitive, typically necessitating backpropagation…

Large-scale deep learning models contribute to significant performance improvements on varieties of downstream tasks. Current data and model parallelism approaches utilize model replication and partition techniques to support the…

Finding effective prompts for language models (LMs) is critical yet notoriously difficult: the prompt space is combinatorially large, rewards are sparse due to expensive target-LM evaluation. Yet, existing RL-based prompt optimizers often…

Group Relative Policy Optimization (GRPO) is a powerful technique for aligning generative models, but its effectiveness is bottlenecked by the conflict between large group sizes and prohibitive computational costs. In this work, we…

Accurate polyp segmentation remains challenging due to irregular lesion morphologies, ambiguous boundaries, and heterogeneous imaging conditions. While U-Net variants excel at local feature fusion, they often lack explicit mechanisms to…

Large-scale deep learning models contribute to significant performance improvements on varieties of downstream tasks. Current data and model parallelism approaches utilize model replication and partition techniques to support the…

The recent success and openness of DeepSeek-R1 have brought widespread attention to Group Relative Policy Optimization (GRPO) as a reinforcement learning method for large reasoning models (LRMs). In this work, we analyze the GRPO objective…

Recent progress in Large Language Model (LLM) reasoning is increasingly driven by the refinement of post-training loss functions and alignment strategies. However, standard Reinforcement Learning (RL) paradigms like Group Relative Policy…

Distributionally robust optimization (DRO) problems are increasingly seen as a viable method to train machine learning models for improved model generalization. These min-max formulations, however, are more difficult to solve. We therefore…

Multi-objective optimization (MOO) lies at the core of many machine learning (ML) applications that involve multiple, potentially conflicting objectives (e.g., multi-task learning, multi-objective reinforcement learning, among many others).…

Parallel implementations of distributed global optimization (DGO) [13] on MP-1 and NCUBE parallel computers revealed an approximate O(n) increase in the performance of this algorithm. Therefore, the implementation of the DGO on parallel…